基于受限分位直方图的小麦苗情图像增强方法
|
摘要
针对物联网监测的小麦苗情图像受成像自然环境和成像设备影响存在对比度低及图像模糊的问题,提出了基于受限分位直方图的小麦苗情图像增强方法,首先压缩高概率密度色彩频度来减少高频色彩的像素出现过增强问题,然后对调整后的直方图进行分位划分以保持图像在增强后的色彩均值信息,缓和图像均值色彩变化过大导致的过增强和噪声放大问题,最后对分位直方图在分位区间内依据累积分布函数分别进行直方图均衡化融合为最终输出图像。结果表明,该方法克服了传统全局直方图易出现的过增强和噪声放大问题,增强后的图像细节丰富,具有更好的视觉效果,能够满足小麦苗情远程监测图像增强的实际应用要求。
Based on the quantile separated and limited image histogram a wheat growth condition image enhancement approach is proposed to deal with the problem of low contrast and blurred image affected by imaging natural environment and imaging equipment. Firstly, the over enhancement problem is alleviated by clipping the number of high frequency pixels in some color channels, and the clipped histogram is then quantile divided to overcome the mean shift problem in traditional image enhancement methods. Finally, each quantile separated image histogram is equalized independently according to the cumulative distribution function and thus the eventual enhanced image can be obtained after the equalization process. The results show that the proposed approach performs better than other relevant global histogram equalization methods and can preserve more image details together with better visual performance compared with the prevailing state of art approaches. Furthermore, it has broad practical application value in the wheat growth image enhancement in the internet of things.
Based on the quantile separated and limited image histogram a wheat growth condition image enhancement approach is proposed to deal with the problem of low contrast and blurred image affected by imaging natural environment and imaging equipment. Firstly, the over enhancement problem is alleviated by clipping the number of high frequency pixels in some color channels, and the clipped histogram is then quantile divided to overcome the mean shift problem in traditional image enhancement methods. Finally, each quantile separated image histogram is equalized independently according to the cumulative distribution function and thus the eventual enhanced image can be obtained after the equalization process. The results show that the proposed approach performs better than other relevant global histogram equalization methods and can preserve more image details together with better visual performance compared with the prevailing state of art approaches. Furthermore, it has broad practical application value in the wheat growth image enhancement in the internet of things.
引文
[1] 杜克明. 小麦生长物联网关键技术研究[D]. 北京:中国农业科学院,2015.
[2] NARASIMHANK,SUDARSHANC R, NAGARAJAN R. A comparison of contrast enhancement techniques in poor illuminated gray level and color images[J]. International Journal of Computer Applications, 2011, 25(2): 17-25.
[3] 许欣. 图像增强若干理论方法与应用研究[D]. 南京:南京理工大学,2010.
[4] TARIK A, SALIH D, YUCEL A. A histogram modification framework and its application for image contrast enhancement[J]. IEEE Transactions on Image Processing, 2009, 18(9):1921-1935.
[5] WANG Q, WARD R K. Fast image/video contrast enhancement based on weighted thresholded histogram equalization[J]. IEEE Transactions on Consumer Electronics, 2007, 53(2): 757-764.
[6] 李锦, 王俊平, 万国挺,等. 一种结合直方图均衡化和MSRCR的图像增强算法[J]. 西安电子科技大学学报(自然科学版), 2014, 41(3): 103-109.
[7] STEPHEN M. PIZER,PHILIP AMBURN E,JOHN AUSTIN D, et al. Adaptive histogram equalization and its variations[J]. Journal of Computer Vision, Graphics, and Image Processing,1987,39(3): 355-368.
[8] 杨卫中, 徐银丽,乔曦,等. 基于对比度受限直方图均衡化的水下海参图像增强方法[J]. 农业工程学报,2016,32(6):197-203.
[9] LIDONG HUANG, WEI ZHAO, ZEBIN SUN, et al. An advanced gradient histogram and its application for contrast and gradient enhancement[J]. J Vis Commun Image R, 2015,31(1):86-100.
[10] Kim Y T.Contrast enhancement using brightness preserving bi-histogram Equalization[J]. IEEE Transactions on Consumer Electronics, 1997,43(1):1-8.
[11] ABDUL GHANI A S, MATLSA NA. Underwater image quality enhancement through integrated color model with Rayleigh distribution[J]. Applied Soft Computing, 2014,27(1):219-230.
[12] IBRAHIM H, KONG NSP. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007,53(4):1752-1758.
[13] TIWARI M, GUPTA B, SHRIVASTAVA M. High speed quantile based histogram equalization for brightness preservation and contrast enhancement[J]. IET Image Processing, 2014, 9(1):80-90.
[14] 吴金建. 基于人类视觉系统的图像信息感知和图像质量评价[D]. 西安:西安电子科技大学,2014.
[15] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[16] Abdullah A L Wadud M,Kabir M H,Ali Akber Dewan M. A dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007, 53(2):593-600.
[17] KIN GWN LORE, ADEDOTUN AKINTAYO, SOUMIK SARKAR. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, 2017, 61(1):650-662.
[2] NARASIMHANK,SUDARSHANC R, NAGARAJAN R. A comparison of contrast enhancement techniques in poor illuminated gray level and color images[J]. International Journal of Computer Applications, 2011, 25(2): 17-25.
[3] 许欣. 图像增强若干理论方法与应用研究[D]. 南京:南京理工大学,2010.
[4] TARIK A, SALIH D, YUCEL A. A histogram modification framework and its application for image contrast enhancement[J]. IEEE Transactions on Image Processing, 2009, 18(9):1921-1935.
[5] WANG Q, WARD R K. Fast image/video contrast enhancement based on weighted thresholded histogram equalization[J]. IEEE Transactions on Consumer Electronics, 2007, 53(2): 757-764.
[6] 李锦, 王俊平, 万国挺,等. 一种结合直方图均衡化和MSRCR的图像增强算法[J]. 西安电子科技大学学报(自然科学版), 2014, 41(3): 103-109.
[7] STEPHEN M. PIZER,PHILIP AMBURN E,JOHN AUSTIN D, et al. Adaptive histogram equalization and its variations[J]. Journal of Computer Vision, Graphics, and Image Processing,1987,39(3): 355-368.
[8] 杨卫中, 徐银丽,乔曦,等. 基于对比度受限直方图均衡化的水下海参图像增强方法[J]. 农业工程学报,2016,32(6):197-203.
[9] LIDONG HUANG, WEI ZHAO, ZEBIN SUN, et al. An advanced gradient histogram and its application for contrast and gradient enhancement[J]. J Vis Commun Image R, 2015,31(1):86-100.
[10] Kim Y T.Contrast enhancement using brightness preserving bi-histogram Equalization[J]. IEEE Transactions on Consumer Electronics, 1997,43(1):1-8.
[11] ABDUL GHANI A S, MATLSA NA. Underwater image quality enhancement through integrated color model with Rayleigh distribution[J]. Applied Soft Computing, 2014,27(1):219-230.
[12] IBRAHIM H, KONG NSP. Brightness preserving dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007,53(4):1752-1758.
[13] TIWARI M, GUPTA B, SHRIVASTAVA M. High speed quantile based histogram equalization for brightness preservation and contrast enhancement[J]. IET Image Processing, 2014, 9(1):80-90.
[14] 吴金建. 基于人类视觉系统的图像信息感知和图像质量评价[D]. 西安:西安电子科技大学,2014.
[15] WANG Z, BOVIK A C, SHEIKH H R, et al. Image quality assessment: from error visibility to structural similarity[J]. IEEE Transactions on Image Processing, 2004, 13(4):600-612.
[16] Abdullah A L Wadud M,Kabir M H,Ali Akber Dewan M. A dynamic histogram equalization for image contrast enhancement[J]. IEEE Transactions on Consumer Electronics, 2007, 53(2):593-600.
[17] KIN GWN LORE, ADEDOTUN AKINTAYO, SOUMIK SARKAR. LLNet: A deep autoencoder approach to natural low-light image enhancement[J]. Pattern Recognition, 2017, 61(1):650-662.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |